Face Detection and Recognition 10/28/10 Chuck Close, self portrait Lucas by Chuck Close Computational Photography Derek Hoiem, University of Illinois Some slides from Lana Lazebnik, Silvio Savarese, Fei-Fei Li

Administrative stuff Previous class? Project 4: vote for faves Midterm (Nov 9) Closed book – can bring one loose-leaf page of notes Some review Nov 4 Project 5 (due Nov 15)

Face detection and recognition “Sally”

Applications of Face Recognition Digital photography

Applications of Face Recognition Digital photography Surveillance

Applications of Face Recognition Digital photography Surveillance Album organization

Consumer application: iPhoto 2009 http://www.apple.com/ilife/iphoto/

Consumer application: iPhoto 2009 Can be trained to recognize pets! http://www.maclife.com/article/news/iphotos_faces_recognizes_cats

What does a face look like?

What does a face look like?

What makes face detection hard? Expression

What makes face detection hard? Viewpoint

What makes face detection hard? Occlusion

What makes face detection hard? Distracting background

What makes face detection and recognition hard? Coincidental textures

Consumer application: iPhoto 2009 Things iPhoto thinks are faces

How to find faces anywhere in an image?

Face detection: sliding windows … Face or Not Face How to deal with multiple scales?

Face classifier Training Testing Training Labels Training Images Image Features Classifier Training Trained Classifier Testing Image Features Trained Classifier Prediction Face Test Image

Face detection … Face or Not Face Face or Not Face

What features? Intensity Patterns (with NNs) (Rowely Baluja Kanade1996) Exemplars (Sung Poggio 1994) Edge (Wavelet) Pyramids (Schneiderman Kanade 1998) Haar Filters (Viola Jones 2000)

How to classify? Many ways Neural networks Adaboost SVMs Nearest neighbor

Statistical Template Object model = log linear model of parts at fixed positions ? +3 +2 -2 -1 -2.5 = -0.5 > 7.5 Non-object ? +4 +1 +0.5 +3 +0.5 = 10.5 > 7.5 Object

Training multiple viewpoints Train new detector for each viewpoint.

Results: faces 208 images with 441 faces, 347 in profile

Results: faces today http://demo.pittpatt.com/

Face recognition Detection Recognition “Sally”

Face recognition Typical scenario: few examples per face, identify or verify test example What’s hard: changes in expression, lighting, age, occlusion, viewpoint Basic approaches (all nearest neighbor) Project into a new subspace (or kernel space) (e.g., “Eigenfaces”=PCA) Measure face features Make 3d face model, compare shape+appearance (e.g., AAM)

What makes face recognition hard? Some of the same stuff Change in expression Occlusion Viewpoint Beards and glasses Age Lots of different faces

Simple idea Treat pixels as a vector Recognize face by nearest neighbor

The space of all face images When viewed as vectors of pixel values, face images are extremely high-dimensional 100x100 image = 10,000 dimensions Slow and lots of storage But very few 10,000-dimensional vectors are valid face images We want to effectively model the subspace of face images

The space of all face images Eigenface idea: construct a low-dimensional linear subspace that best explains the variation in the set of face images

Principal Component Analysis (PCA) Given: N data points x1, … ,xN in Rd We want to find a new set of features that are linear combinations of original ones: u(xi) = uT(xi – µ) (µ: mean of data points) Choose unit vector u in Rd that captures the most data variance Forsyth & Ponce, Sec. 22.3.1, 22.3.2

Principal Component Analysis Direction that maximizes the variance of the projected data: N Maximize subject to ||u||=1 Projection of data point N 1/N Covariance matrix of data The direction that maximizes the variance is the eigenvector associated with the largest eigenvalue of Σ

Implementation issue Covariance matrix is huge (N2 for N pixels) But typically # examples << N Simple trick X is matrix of normalized training data Solve for eigenvectors u of XXT instead of XTX Then XTu is eigenvector of covariance XTX May need to normalize (to get unit length vector)

Eigenfaces (PCA on face images) Compute covariance matrix of face images Compute the principal components (“eigenfaces”) K eigenvectors with largest eigenvalues Represent all face images in the dataset as linear combinations of eigenfaces Perform nearest neighbor on these coefficients M. Turk and A. Pentland, Face Recognition using Eigenfaces, CVPR 1991

Eigenfaces example Training images x1,…,xN

Top eigenvectors: u1,…uk Eigenfaces example Top eigenvectors: u1,…uk Mean: μ

Visualization of eigenfaces Principal component (eigenvector) uk μ + 3σkuk μ – 3σkuk

Representation and reconstruction Face x in “face space” coordinates: =

Representation and reconstruction Face x in “face space” coordinates: Reconstruction: = = + ^ x = µ + w1u1+w2u2+w3u3+w4u4+ …

Reconstruction P = 4 P = 200 P = 400 After computing eigenfaces using 400 face images from ORL face database

Eigenvalues (variance along eigenvectors)

Note Preserving variance (minimizing MSE) does not necessarily lead to qualitatively good reconstruction. P = 200

Recognition with eigenfaces Process labeled training images Find mean µ and covariance matrix Σ Find k principal components (eigenvectors of Σ) u1,…uk Project each training image xi onto subspace spanned by principal components: (wi1,…,wik) = (u1T(xi – µ), … , ukT(xi – µ)) Given novel image x Project onto subspace: (w1,…,wk) = (u1T(x – µ), … , ukT(x – µ)) Optional: check reconstruction error x – x to determine whether image is really a face Classify as closest training face in k-dimensional subspace ^ M. Turk and A. Pentland, Face Recognition using Eigenfaces, CVPR 1991

PCA General dimensionality reduction technique Preserves most of variance with a much more compact representation Lower storage requirements (eigenvectors + a few numbers per face) Faster matching What are the problems for face recognition?

Limitations Global appearance method: not robust to misalignment, background variation

Limitations The direction of maximum variance is not always good for classification

A more discriminative subspace: FLD Fisher Linear Discriminants  “Fisher Faces” PCA preserves maximum variance FLD preserves discrimination Find projection that maximizes scatter between classes and minimizes scatter within classes Reference: Eigenfaces vs. Fisherfaces, Belheumer et al., PAMI 1997

Illustration Objective: Within class scatter Between class scatter x2

Comparing with PCA

Recognition with FLD Similar to “eigenfaces” Compute within-class and between-class scatter matrices Solve generalized eigenvector problem Project to FLD subspace and classify by nearest neighbor

Large scale comparison of methods FRVT 2006 Report Not much (or any) information available about methods, but gives idea of what is doable

FVRT Challenge Frontal faces FVRT2006 evaluation: computers win!

Another cool method: attributes for face verification Kumar et al. 2009

Attributes for face verification Kumar et al. 2009

Attributes for face verification

Face recognition by humans Face recognition by humans: 20 results (2005) Slides by Jianchao Yang

Result 17: Vision progresses from piecemeal to holistic

Things to remember Face detection via sliding window search Features are important PCA is a generally useful dimensionality reduction technique But not ideal for discrimination FLD better for discrimination, though only ideal under Gaussian data assumptions Computer face recognition works very well under controlled environments – still lots of room for improvement in general conditions

Next class Things you can do with lots of data